Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

DASH: A Bimodal Data Exploration Tool for Interactive Text and Visualizations

Dennis Bromley, Vidya Setlur

TL;DR

Dash addresses the challenge of integrating long-form text with visual data by introducing a bimodal exploration tool that uses a four-level semantic hierarchy ($L1$-$L4$) and LLM-generated narratives to link text and charts. It operationalizes the semantic framework to enable bidirectional text-chart interactions via drag-and-drop, demonstrated on a Seattle real estate dataset in a preliminary evaluation. The approach contributes a production-like metadata scheme, a practical interface for bimodal data exploration, and insights into user needs such as semantic-layer granularity and LLM reliability. The work signals a path toward richer data storytelling and interactive analysis in data visualization environments.

Abstract

Integrating textual content, such as titles, annotations, and captions, with visualizations facilitates comprehension and takeaways during data exploration. Yet current tools often lack mechanisms for integrating meaningful long-form prose with visual data. This paper introduces DASH, a bimodal data exploration tool that supports integrating semantic levels into the interactive process of visualization and text-based analysis. DASH operationalizes a modified version of Lundgard et al.'s semantic hierarchy model that categorizes data descriptions into four levels ranging from basic encodings to high-level insights. By leveraging this structured semantic level framework and a large language model's text generation capabilities, DASH enables the creation of data-driven narratives via drag-and-drop user interaction. Through a preliminary user evaluation, we discuss the utility of DASH's text and chart integration capabilities when participants perform data exploration with the tool.

DASH: A Bimodal Data Exploration Tool for Interactive Text and Visualizations

TL;DR

Dash addresses the challenge of integrating long-form text with visual data by introducing a bimodal exploration tool that uses a four-level semantic hierarchy (-) and LLM-generated narratives to link text and charts. It operationalizes the semantic framework to enable bidirectional text-chart interactions via drag-and-drop, demonstrated on a Seattle real estate dataset in a preliminary evaluation. The approach contributes a production-like metadata scheme, a practical interface for bimodal data exploration, and insights into user needs such as semantic-layer granularity and LLM reliability. The work signals a path toward richer data storytelling and interactive analysis in data visualization environments.

Abstract

Integrating textual content, such as titles, annotations, and captions, with visualizations facilitates comprehension and takeaways during data exploration. Yet current tools often lack mechanisms for integrating meaningful long-form prose with visual data. This paper introduces DASH, a bimodal data exploration tool that supports integrating semantic levels into the interactive process of visualization and text-based analysis. DASH operationalizes a modified version of Lundgard et al.'s semantic hierarchy model that categorizes data descriptions into four levels ranging from basic encodings to high-level insights. By leveraging this structured semantic level framework and a large language model's text generation capabilities, DASH enables the creation of data-driven narratives via drag-and-drop user interaction. Through a preliminary user evaluation, we discuss the utility of DASH's text and chart integration capabilities when participants perform data exploration with the tool.
Paper Structure (13 sections, 1 figure, 1 table)

This paper contains 13 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Typologies and taxonomies for analytical tasks
  4. The role of text in visual analytics
  5. Visualization and text tools
  6. Dash Tool
  7. Motivation
  8. Applying semantic levels for data exploration
  9. Implementation
  10. Interface and Interactivity Behavior
  11. Preliminary Evaluation
  12. Results and Discussion
  13. Future Directions for Bimodal Data Analysis

Figures (1)

  • Figure 1: The Dash interface and an associated interactivity example. Generated text paragraphs are labeled as Px, and interactive mouse-drag gestures are labeled as Ix. The Dash interface comprises two primary sections: the text area on the left and the chart area on the right. The Tell Me More and Show Me More buttons at the bottom left trigger additional text and chart rendering, respectively. Text-to-text (I1), text-to-chart (I2-I5), chart-to-chart (I6), and chart-to-text (I7) interactions are illustrated.